Machine Learning-Assisted Classification of Paraffin-Embedded Brain Tumors with Raman Spectroscopy
Brain Sciences · 23.03.2024 · 14 (4) · 301
DOI: 10.3390/brainsci14040301 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 23.03.2024. Verfasst von Gilbert Georg Klamminger und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of General and Special Pathology, Saarland University (USAAR), 66424 Homburg, Germany. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fondation Cancer (Luxembourg) and Luxembourg National Research Fond, Luxembourg National Research Fund, FNR, Fondation Cancer, Luxembourg.
Abstract (Originalsprache)
Raman spectroscopy (RS) has demonstrated its utility in neurooncological diagnostics, spanning from intraoperative tumor detection to the analysis of tissue samples peri- and postoperatively. In this study, we employed Raman spectroscopy (RS) to monitor alterations in the molecular vibrational characteristics of a broad range of formalin-fixed, paraffin-embedded (FFPE) intracranial neoplasms (including primary brain tumors and meningiomas, as well as brain metastases) and considered specific challenges when employing RS on FFPE tissue during the routine neuropathological workflow. We spectroscopically measured 82 intracranial neoplasms on CaF2 slides (in total, 679 individual measurements) and set up a machine learning framework to classify spectral characteristics by splitting our data into training cohorts and external validation cohorts. The effectiveness of our machine learning algorithms was assessed by using common performance metrics such as AUROC and AUPR values. With our trained random forest algorithms, we distinguished among various types of gliomas and identified the primary origin in cases of brain metastases. Moreover, we spectroscopically diagnosed tumor types by using biopsy fragments of pure necrotic tissue, a task unattainable through conventional light microscopy. In order to address misclassifications and enhance the assessment of our models, we sought out significant Raman bands suitable for tumor identification. Through the validation phase, we affirmed a considerable complexity within the spectroscopic data, potentially arising not only from the biological tissue subjected to a rigorous chemical procedure but also from residual components of the fixation and paraffin-embedding process. The present study demonstrates not only the potential applications but also the constraints of RS as a diagnostic tool in neuropathology, considering the challenges associated with conducting vibrational spectroscopic analysis on formalin-fixed, paraffin-embedded (FFPE) tissue.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of General and Special Pathology, Saarland University (USAAR), 66424 Homburg, Germany.
- Department of General and Special Pathology, Saarland University Medical Center (UKS), 66424 Homburg, Germany.
- National Center of Pathology (NCP), Laboratoire National de Santé (LNS), 3555 Dudelange, Luxembourg.
- Luxembourg Center of Neuropathology (LCNP), 3555 Dudelange, Luxembourg.
- National Center of Neurosurgery, Centre Hospitalier de Luxembourg (CHL), 1210 Luxembourg, Luxembourg.
- Doctoral School in Science and Engineering (DSSE), University of Luxembourg (UL), 4362 Esch-sur-Alzette, Luxembourg.
ORCID-Profile: Gilbert Georg Klamminger, Andreas Husch, Felix B Kleine Borgmann
Förderung
- Fondation Cancer (Luxembourg) and Luxembourg National Research Fond
- Luxembourg National Research Fund, FNR
- Fondation Cancer, Luxembourg
Zitieren
APA
Klamminger, G. G., Mombaerts, L., Kemp, F., Jelke, F., Klein, K., Slimani, R., Mirizzi, G., Husch, A., Hertel, F., Mittelbronn, M., & Kleine Borgmann, F. B. (2024). Machine Learning-Assisted Classification of Paraffin-Embedded Brain Tumors with Raman Spectroscopy. Brain Sciences, 14(4), 301. https://doi.org/10.3390/brainsci14040301
Vancouver
Klamminger GG, Mombaerts L, Kemp F, Jelke F, Klein K, Slimani R, et al. Machine Learning-Assisted Classification of Paraffin-Embedded Brain Tumors with Raman Spectroscopy. Brain Sciences. 2024;14(4):301. doi:10.3390/brainsci14040301
BibTeX
@article{Klamminger2024,
author = {Klamminger, Gilbert Georg and Mombaerts, Laurent and Kemp, Françoise and Jelke, Finn and Klein, Karoline and Slimani, Rédouane and Mirizzi, Giulia and Husch, Andreas and Hertel, Frank and Mittelbronn, Michel and Kleine Borgmann, Felix B},
title = {Machine Learning-Assisted Classification of Paraffin-Embedded Brain Tumors with Raman Spectroscopy},
journal = {Brain Sciences},
year = {2024},
volume = {14},
number = {4},
pages = {301},
doi = {10.3390/brainsci14040301}
}
EUVIMED